Apache Druid MCP Server

Apache Druid MCP Server

Enables querying and managing Apache Druid datasources through natural language, including SQL queries, datasource exploration, and cluster connectivity testing.

Category
访问服务器

README

Apache Druid MCP Server

Model Context Protocol (MCP) server for Apache Druid - provides tools and resources for querying and managing Druid datasources through Claude Desktop, VS Code, and other MCP clients.

Features

  • 🔍 Execute SQL queries against Apache Druid
  • 📊 List and explore datasources
  • 📋 Get detailed metadata including schema, segments, and size information
  • 🔗 Test Druid cluster connectivity
  • 🚀 Multiple transport protocols: stdio (default) and Server-Sent Events (SSE)
  • 🐳 Docker support via published image

Quick Start

NPX (Recommended)

npx apache-druid-mcp

Docker

# Run with SSE transport
docker run -p 3000:3000 \
  -e DRUID_URL=https://your-druid-cluster.com:8888 \
  -e DRUID_USERNAME=your-username \
  -e DRUID_PASSWORD=your-password \
  anilreddy399/apache-druid-mcp:latest --transport sse --port 3000

# Run with stdio transport (for direct MCP communication)
docker run -i \
  -e DRUID_URL=https://your-druid-cluster.com:8888 \
  -e DRUID_USERNAME=your-username \
  -e DRUID_PASSWORD=your-password \
  anilreddy399/apache-druid-mcp:latest

Local Development

npm install
npm run build
npm start

Configuration

Environment Variables

  • DRUID_URL - Druid router/broker URL (default: http://localhost:8888)
  • DRUID_USERNAME - Authentication username (required for most production clusters)
  • DRUID_PASSWORD - Authentication password (required for most production clusters)
  • DRUID_TIMEOUT - Request timeout in milliseconds (default: 30000)

Transport Options

# Default stdio transport (for MCP clients)
apache-druid-mcp

# SSE transport for HTTP-based clients
apache-druid-mcp --transport sse --port 3000

Claude Desktop Integration

Add this configuration to your Claude Desktop config file:

macOS

~/Library/Application Support/Claude/claude_desktop_config.json

Windows

%APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "apache-druid": {
      "command": "npx",
      "args": ["apache-druid-mcp"],
      "env": {
        "DRUID_URL": "https://your-druid-cluster.com:8888",
        "DRUID_USERNAME": "your-username",
        "DRUID_PASSWORD": "your-password"
      }
    }
  }
}

For local development (no authentication):

{
  "mcpServers": {
    "apache-druid": {
      "command": "npx", 
      "args": ["apache-druid-mcp"],
      "env": {
        "DRUID_URL": "http://localhost:8888"
      }
    }
  }
}

VS Code Integration

Using MCP Extension

  1. Install the MCP extension for VS Code
  2. Add to your VS Code settings.json:
{
  "mcp.servers": {
    "apache-druid": {
      "command": "npx",
      "args": ["apache-druid-mcp"],
      "env": {
        "DRUID_URL": "https://your-druid-cluster.com:8888",
        "DRUID_USERNAME": "your-username",
        "DRUID_PASSWORD": "your-password"
      }
    }
  }
}

Using Codeium or Continue.dev

For HTTP-based AI coding assistants, use SSE transport:

{
  "mcpServers": [
    {
      "name": "apache-druid",
      "url": "http://localhost:3000/sse",
      "env": {
        "DRUID_URL": "https://your-druid-cluster.com:8888",
        "DRUID_USERNAME": "your-username",
        "DRUID_PASSWORD": "your-password"
      }
    }
  ]
}

Start the server with SSE transport:

npx apache-druid-mcp --transport sse --port 3000

Available Tools

The MCP server provides these tools for interacting with Apache Druid:

execute_sql_query

Execute SQL queries against Druid datasources.

Parameters:

  • query (string, required) - SQL query to execute
  • context (object, optional) - Query context parameters

Example:

SELECT __time, page, COUNT(*) as views 
FROM wikipedia 
WHERE __time >= CURRENT_TIMESTAMP - INTERVAL '1' HOUR 
GROUP BY 1, 2 
ORDER BY views DESC 
LIMIT 10

list_datasources

Get a list of all available datasources in the Druid cluster.

get_datasource_metadata

Get detailed metadata for a specific datasource including schema, segments, size, and intervals.

Parameters:

  • datasource (string, required) - Name of the datasource

test_connection

Test connectivity to the Druid cluster and return status information.

Available Resources

Access Druid cluster information through these resources:

  • druid://cluster/status - Current cluster status and health
  • druid://datasources - List of all datasources
  • druid://datasource/{name} - Detailed metadata for specific datasource

Examples

Basic Usage

# Start with default settings
npx apache-druid-mcp

# Connect to remote Druid cluster
DRUID_URL=https://druid.example.com:8888 npx apache-druid-mcp

# With authentication
DRUID_URL=https://secure-druid.com:8888 \
DRUID_USERNAME=admin \
DRUID_PASSWORD=secret \
npx apache-druid-mcp

Using with Claude Desktop

Once configured, you can ask Claude:

  • "Show me the available datasources in Druid"
  • "Query the wikipedia datasource for top pages in the last hour"
  • "What's the schema of the events datasource?"
  • "Test the connection to Druid"

Advanced Configuration

# Custom timeout and SSE transport
DRUID_TIMEOUT=60000 npx apache-druid-mcp --transport sse --port 8080

License

Apache License 2.0

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选